{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:25:49Z","timestamp":1780511149236,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681853","type":"print"},{"value":"9789819681860","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-8186-0_6","type":"book-chapter","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:18:00Z","timestamp":1750155480000},"page":"65-77","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Industrial Anomaly Segmentation with\u00a0Image-Aware Prompt Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7755-0041","authenticated-orcid":false,"given":"SoYoung","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9573-2916","authenticated-orcid":false,"given":"Hyewon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2909-150X","authenticated-orcid":false,"given":"Mingyu","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3393-4797","authenticated-orcid":false,"given":"Seunghoon","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0774-3619","authenticated-orcid":false,"given":"Jong-Ryul","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5924-3398","authenticated-orcid":false,"given":"Sungsu","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4522-5388","authenticated-orcid":false,"given":"Tae-Ho","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"6_CR1","unstructured":"Aota, T., Tong, L.T.T., Okatani, T.: Zero-shot versus many-shot: unsupervised texture anomaly detection. In: WACV, pp. 5564\u20135572 (2023). https:\/\/drive.google.com\/drive\/folders\/10OyPzvI3H6llCZBxKxFlKWt1Pw1tkMK1\/"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bao, T., et al.: MIAD: a maintenance inspection dataset for unsupervised anomaly detection. In: ICCV, pp. 993\u20131002 (2023)","DOI":"10.1109\/ICCVW60793.2023.00106"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD\u2013a comprehensive real-world dataset for unsupervised anomaly detection. In: CVPR, pp. 9592\u20139600 (2019). https:\/\/www.mvtec.com\/downloads\/","DOI":"10.1109\/CVPR.2019.00982"},{"key":"6_CR4","unstructured":"Cao, Y., et al.: Segment any anomaly without training via hybrid prompt regularization. arXiv preprint arXiv:2305.10724 (2023)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: CLIP-AD: a language-guided staged dual-path model for zero-shot anomaly detection. In: IJCAI, pp. 17\u201333 (2024)","DOI":"10.1007\/978-981-97-9003-6_2"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Y., Qiu, C., Yuan, K.: Surface defect saliency of magnetic tile. Vis. Comput. 36(1), 85\u201396 (2020). https:\/\/github.com\/abin24\/Magnetic-tile-defect-datasets.\/","DOI":"10.1007\/s00371-018-1588-5"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Jeong, J., Zou, Y., Kim, T., Zhang, D., Ravichandran, A., Dabeer, O.: WinCLIP: Zero-\/Few-Shot anomaly classification and segmentation. In: CVPR, pp. 19606\u201319616 (2023)","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Jezek, S., Jonak, M., Burget, R., Dvorak, P., Skotak, M.: Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In: ICUMT, pp. 66\u201371 (2021). https:\/\/github.com\/stepanje\/MPDD\/","DOI":"10.1109\/ICUMT54235.2021.9631567"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Lee, M., Choi, J.: Text-guided variational image generation for industrial anomaly detection and segmentation. In: CVPR, pp. 26519\u201326528 (2024)","DOI":"10.1109\/CVPR52733.2024.02504"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, X., Zhao, H., Wang, S., Zhong, Y.: Anomaly segmentation for high-resolution remote sensing images based on pixel descriptors. In: AAAI, pp. 4426\u20134434 (2023)","DOI":"10.1609\/aaai.v37i4.25563"},{"key":"6_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129122","volume":"618","author":"S Li","year":"2025","unstructured":"Li, S., Cao, J., Ye, P., Ding, Y., Tu, C., Chen, T.: ClipSAM: CLIP and SAM collaboration for zero-shot anomaly segmentation. Neurocomputing 618, 129122 (2025)","journal-title":"Neurocomputing"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Goodge, A., Liu, F., Foo, C.S.: PromptAD: zero-shot anomaly detection using text prompts. In: WACV, pp. 1093\u20131102 (2024)","DOI":"10.1109\/WACV57701.2024.00113"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: ECCV, pp. 38\u201355 (2025)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: CVPR, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"6_CR16","unstructured":"Ma, H., et al.: Fairness-guided few-shot prompting for large language models. In: NeurIPS, pp. 43136\u201343155 (2023)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Mishra, P., Verk, R., Fornasier, D., Piciarelli, C., Foresti, G.L.: VT-ADL: a vision transformer network for image anomaly detection and localization. In: ISIE, pp. 01\u201306 (2021). http:\/\/avires.dimi.uniud.it\/papers\/btad\/btad.zip","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"6_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Tabernik, D., \u0160ela, S., Skvar\u010d, J., Sko\u010daj, D.: Segmentation-based deep-learning approach for surface-defect detection. J. Intell. Manuf. 31(3), 759\u2013776 (2020). https:\/\/www.vicos.si\/resources\/kolektorsdd\/","DOI":"10.1007\/s10845-019-01476-x"},{"key":"6_CR20","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: CLIP-driven referring image segmentation. In: CVPR, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"6_CR22","unstructured":"Wieler, M., Hahn, T., Hamprecht, F.A.: Weakly supervised learning for industrial optical inspection (2007). https:\/\/conferences.mpi-inf.mpg.de\/dagm\/2007\/prizes.html"},{"issue":"11","key":"6_CR23","doi-asserted-by":"publisher","first-page":"1536","DOI":"10.1111\/mice.12954","volume":"38","author":"G Yong","year":"2023","unstructured":"Yong, G., Jeon, K., Gil, D., Lee, G.: Prompt engineering for zero-shot and few-shot defect detection and classification using a visual-language pretrained model. Comput.-Aid. Civil Infrastruct. Eng. 38(11), 1536\u20131554 (2023)","journal-title":"Comput.-Aid. Civil Infrastruct. Eng."},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Text2Seg: zero-shot remote sensing image semantic segmentation via text-guided visual foundation models. In: GeoAI@SIGSPATIAL, pp. 63\u201366 (2024)","DOI":"10.1145\/3687123.3698287"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et\u00a0al.: Recognize anything: a strong image tagging model. In: CVPR, pp. 1724\u20131732 (2024)","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"6_CR26","unstructured":"Zhang, Y., et al.: EVF-SAM: early vision-language fusion for text-prompted segment anything model. arXiv preprint arXiv:2406.20076 (2024)"},{"key":"6_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109045","volume":"177","author":"J Zipfel","year":"2023","unstructured":"Zipfel, J., Verworner, F., Fischer, M., Wieland, U., Kraus, M., Zschech, P.: Anomaly detection for industrial quality assurance: a comparative evaluation of unsupervised deep learning models. Comput. Ind. Eng. 177, 109045 (2023)","journal-title":"Comput. Ind. Eng."}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8186-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:18:07Z","timestamp":1750155487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8186-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681853","9789819681860"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8186-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}